# Cross-domain Calibration on miniImageNet to CUB (test)

Source: [Cross-domain Calibration on miniImageNet to CUB (test)](<https://www.sota2.com/research/sota/cross-domain-calibration-on-miniimagenet-to-cub-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:41:20.774Z

Evaluation of model calibration performance when transferring knowledge from miniImageNet to the CUB dataset (test split), measured using metrics like ECE, MCE, and Brier score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Cross-domain Calibration |
| Dataset (including any stated split) | miniImageNet -\> CUB (test) |
| Metric | ECE |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [ECE](<https://www.sota2.com/research/sota/cross-domain-calibration-on-miniimagenet-to-cub-test.md?metric=ECE>): Lower is better; unit: PERCENT.

- [MCE](<https://www.sota2.com/research/sota/cross-domain-calibration-on-miniimagenet-to-cub-test.md?metric=MCE>): Lower is better; unit: PERCENT.

- [Brier Score](<https://www.sota2.com/research/sota/cross-domain-calibration-on-miniimagenet-to-cub-test.md?metric=Brier%20Score>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ECE | Result date | Report paper |
| --- | --- | --- | --- |
| Proto Nets | 0.9 | Not recorded | 68fa6d4f1e209131cea3906e |
| TRIDENT | 0.9 | Not recorded | 68fa6d4f1e209131cea3906e |
| OVE(PL) | 2 | Not recorded | 68fa6d4f1e209131cea3906e |
| LogSoftGP(PL) | 2.2 | Not recorded | 68fa6d4f1e209131cea3906e |
| Matching Nets | 3 | Not recorded | 68fa6d4f1e209131cea3906e |
| BMAML | 4.8 | Not recorded | 68fa6d4f1e209131cea3906e |
| OVE(ML) | 4.9 | Not recorded | 68fa6d4f1e209131cea3906e |
| BMAML+Chaser | 6.6 | Not recorded | 68fa6d4f1e209131cea3906e |
| LogSoftGP(ML) | 22 | Not recorded | 68fa6d4f1e209131cea3906e |
| Relation Net | 23.4 | Not recorded | 68fa6d4f1e209131cea3906e |
| DKT+Cos | 23.6 | Not recorded | 68fa6d4f1e209131cea3906e |
| Feature Transfer | 27.5 | Not recorded | 68fa6d4f1e209131cea3906e |
| Baseline | 31.5 | Not recorded | 68fa6d4f1e209131cea3906e |

### Proto Nets

ECE: 0.9. Result ID: 698f9ba53a6c314849fa7c85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa636e1e209131ce9febd3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TRIDENT

ECE: 0.9. Result ID: 698f9ba53a6c314849fa7c8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Implementation](<https://github.com/anujinho/trident>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OVE(PL)

ECE: 2. Result ID: 698f9ba53a6c314849fa7c8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687e1e209131cea1c505.md>)

[Implementation](<https://github.com/BayesWatch/deep-kernel-transfer>)

Recorded evaluation configuration: {"Objective":"Pseudo-Likelihood"}. This record does not assert independent reproduction.

### LogSoftGP(PL)

ECE: 2.2. Result ID: 698f9ba53a6c314849fa7c8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c420.md>)

Recorded evaluation configuration: {"Objective":"Pseudo-Likelihood"}. This record does not assert independent reproduction.

### Matching Nets

ECE: 3. Result ID: 698f9ba53a6c314849fa7c84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63e81e209131cea015ca.md>)

[Implementation](<https://goo.gl/e3orz6>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BMAML

ECE: 4.8. Result ID: 698f9ba53a6c314849fa7c88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65121e209131cea07fa2.md>)

Recorded evaluation configuration: {"Variation":"Base"}. This record does not assert independent reproduction.

### OVE(ML)

ECE: 4.9. Result ID: 698f9ba53a6c314849fa7c8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69161e209131cea201eb.md>)

Recorded evaluation configuration: {"Objective":"Marginal Likelihood"}. This record does not assert independent reproduction.

### BMAML+Chaser

ECE: 6.6. Result ID: 698f9ba53a6c314849fa7c89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65121e209131cea07fa2.md>)

Recorded evaluation configuration: {"Variation":"Chaser"}. This record does not assert independent reproduction.

### LogSoftGP(ML)

ECE: 22. Result ID: 698f9ba53a6c314849fa7c8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c420.md>)

Recorded evaluation configuration: {"Objective":"Marginal Likelihood"}. This record does not assert independent reproduction.

### Relation Net

ECE: 23.4. Result ID: 698f9ba53a6c314849fa7c86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64301e209131cea03588.md>)

[Implementation](<https://github.com/lzrobots/DeepEmbeddingModel_ZSL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DKT+Cos

ECE: 23.6. Result ID: 698f9ba53a6c314849fa7c87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687e1e209131cea1c505.md>)

[Implementation](<https://github.com/BayesWatch/deep-kernel-transfer>)

Recorded evaluation configuration: {"Kernel":"Cosine"}. This record does not assert independent reproduction.

### Feature Transfer

ECE: 27.5. Result ID: 698f9ba53a6c314849fa7c82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e41e209131cea12e8a.md>)

[Implementation](<https://github.com/wyharveychen/CloserLookFewShot>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Baseline

ECE: 31.5. Result ID: 698f9ba53a6c314849fa7c83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4f1e209131cea3906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e41e209131cea12e8a.md>)

[Implementation](<https://github.com/wyharveychen/CloserLookFewShot>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.